Tejas Latne

Bio: Tejas Latne is an academic researcher from Vishwakarma Institute of Technology. The author has contributed to research in topics: Biometrics. The author has an hindex of 1, co-authored 1 publications receiving 12 citations.

Biometric Recognition Using Fusion

Abstract: Human identification systems based on biometrics are used in many applications to increase the security level. There are different biometric traits which are used in various applications. Monomodal biometric systems face many challenges such as error rates, using only single biometric for human recognition. Today, to increase the security of the authentication system, various multimodal biometric systems are proposed. A multimodal biometric system uses more than one biometric trait or modality for recognition of an individual. Multimodal biometric systems fuses different types of input at different level: Score level, Feature level and Decision level to get the better performance of the system.

Multimodal biometric authentication using fingerprint and iris recognition in identity management

Abstract: The majority of deployed biometric systems today use information from a single biometric technology for verification or identification. Large-scale biometric systems have to address additional demands such as larger population coverage and demographic diversity, varied deployment environment, and more demanding performance requirements. Today's single modality biometric systems are finding it difficult to meet these demands, and a solution is to integrate additional sources of information to strengthen the decision process. A multibiometric system combines information from multiple biometric traits, algorithms, sensors, and other components to make a recognition decision. Besides improving the accuracy, the fusion of biometrics has several advantages such as increasing population coverage, deterring spoofing activities and reducing enrolment failure. The last 5 years have seen an exponential growth in research and commercialization activities in this area, and this trend is likely to continue. Therefore, here we propose a novel multimodal biometric authentication approach fusing iris and fingerprint traits at score-level. We principally explore the fusion of iris and fingerprint biometrics and their potential application as biometric identifiers. The individual comparison scores obtained from the iris and fingerprints are combined at score-level using a three score normalization techniques (Min-Max, Z-Score, Hyperbolic Tangent) and four score fusion approaches (Minimum Score, Maximum Score Simple Sum and User Weighting). The fused-score is utilized to classify an unknown user into the genuine or impostor.

Voice recognition system using machine learning techniques

Abstract: Voice is a Special metric that, in addition to being natural to users, offers similar, if not higher, levels of security when compared to some traditional biometrics systems. The aim of this paper is to detect impostors using various machine learning techniques to see which combination works best for speaker recognition and classification. We present several methods of audio preprocessing, such as noise reduction and vocal enhancements, to improve the audios available in real environments. Mel Frequency Cepstral Coefficients (MFCC) are extracted for each audio, along with their differentials and accelerations, to verify machine learning classification methods such as PART, JRip, Nave Bayes, RT, J48, Random Forest, and k-Nearest Neighbor Classifiers. examine the 7 classifiers on two datasets, the extent of accuracy achieved for each classifier. Among the high performance were the random forest algorithm and the naive bias algorithm, and the weak performance of the PART algorithm.

Development of a remote health care wireless sensor network based on wireless spread spectrum communication networks

Abstract: When medical technology, communication, and computers were developed and put into practice in the treatment and follow-up of remote health care patients, the difficulty of communicating with the medical team or patients was due to bandwidth limitations. Sending a significant volume of data between medical personnel and patients, as well as power usage, is not permitted. Wireless sensors use a direct spread spectrum based on CDMA, especially mobile wireless third generation with a wide bandwidth that can send large data such as multimedia between patients and doctors at anytime and anywhere. The wireless sensor network decreases the power consumption of the transmitter sensor and the receiver sensor by using binary transmission and multipath. The accuracy of the measurement depends on the bandwidth of the unit to calculate the time of arrival (TOA). The TOA forecasts come and go together to pass them to the receiver because of the delay of the MPC and the reduction of replicas of the initial signal. The diffusion time caused by the moving signal through barriers, adding a positive bias to the TOA.

Downdraft gasifier design calculation for biomass gasification using exhaust gas as a gasification agent

Abstract: This work aims to design, build, and commission a downdraft gasifier of 1 MW for electricity purposes. Wood pellets were the feedstock at a feeding rate of 300 kg/hr. A reaction temperature's range from 700⁰C to 974⁰C was reached by controlling the equivalence ratio. Replacing the airflow with exhaust gasses led to getting a temperature of (620–850 ⁰C), using wet biomass instead of the drying one led to having a reaction temperature of 830–1070 ⁰C, which is almost the same in the case of air and that of the exhaust gas. The temperature of the produced syngas at the outlet was found between 180⁰C to 220⁰C. The analysis of the produced syngas shows that carbon monoxide: 14.4–19.2%, hydrogen 16–20%, carbon dioxide 7.1–11.2%, and a small volume of methane 2–3%. Such built downdraft gasifiers could be a prospective system for developing countries as essential electricity and green energy source.

Intelligent system for imposter detection: Asurvey

Abstract: This study aims the impostor is a very cunning person who reaches an obsessive stage to perfection in impersonating someone in actual life, concentrates on his biometric. He analyzes the controls, restrictions, and obstacles that he will face to overcome them. The technologies biometric recognition performs a greatly important role in impostor detection. Biometrics properties refer to the automatic recognition of persons depending on their behavioral and physiological characteristics. Biometrics comprises face recognition, fingerprint, voice recognition, retinal scanning, and so on. Biometrics may increment the reliability of an ID card system. In this paper, a review of the concepts mentioned above will be provided. At first, a presentation about a procedural overview of biometric recognition technologies, ID card systems. Then dissection will be presented for the review of the most recent techniques. A description of each concept will be given and a comparison study is achieved with formal discussion and analysis for each approach result introduces in this study. Finally, a summary of the research results is given.